P
US9830375B2ActiveUtilityPatentIndex 33

Apparatus for selecting and providing media content on social network service and method thereof

Assignee: KOREA INST SCI & TECHPriority: Mar 13, 2014Filed: Jun 13, 2014Granted: Nov 28, 2017
Est. expiryMar 13, 2034(~7.7 yrs left)· nominal 20-yr term from priority
Inventors:KWON YONG MOOPARK JAEHYUKBUTT ABBAS ALI
G06F 17/30595H04L 51/32H04L 51/52G06F 16/284
33
PatentIndex Score
0
Cited by
20
References
18
Claims

Abstract

Disclosed is an apparatus and method for selecting and providing media content on a social network service (SNS), and the apparatus includes a media content search unit configured to search, from a SNS server which contains media content composed of images or text, for media content related to a user accessing the SNS server, a media content processing unit configured to determine at least one piece of media content among the retrieved media content as candidate media content by analyzing an image, text, or metadata of the retrieved media content, and a service providing unit configured to provide the determined candidate media content to the user.

Claims

exact text as granted — not AI-modified
What is claimed is: 
     
       1. An apparatus to select and provide media content on a social network service (SNS), the apparatus comprising:
 a media content searcher, implemented by a hardware-based processor, configured to search media content related to a user accessing an SNS server, wherein the media content comprises either one or both of an image and text; 
 a media content processor, implemented by the hardware-based processor, configured to
 calculate a representativeness score for each piece of the media content as a weighted sum of any combination of any two or more of a number of likes, a number of shares, and information associated with a friend of the user on the SNS who liked or shared the media content, wherein weights of the weighted sum are based on a number of words in a comment and a number of friends who wrote comments, 
 select the each piece of the media content having the representative score greater than or equal to a threshold, and 
 group the selected each piece of the media content using a K-means clustering algorithm; and 
 
 a service provider, implemented by the hardware-based processor, configured to provide the grouped selected each piece of the media content to the user. 
 
     
     
       2. The apparatus according to  claim 1 , further comprising a communication interface unit configured to access the SNS server. 
     
     
       3. The apparatus according to  claim 1 , wherein the SNS server comprises a plurality of SNS servers that provide different SNSs. 
     
     
       4. The apparatus according to  claim 1 , wherein the image is a still image or a dynamic image. 
     
     
       5. The apparatus according to  claim 1 , wherein the text comprises a title of the media content, a body of the media content, or a comment of the media content. 
     
     
       6. The apparatus according to  claim 5 , wherein the media content processor is further configured to determine the selected each piece of the media content using metadata comprising any one or any combination of creation time information, edited time information, locational information, a file name, a file format, the number of likes, the number of shares of the media content, and the information associated with the friend of the user on the SNS who liked or shared the media content. 
     
     
       7. The apparatus according to  claim 6 , wherein the media content processor is further configured to calculate the representativeness score by analyzing the text or the metadata. 
     
     
       8. The apparatus according to  claim 7 , wherein the media content processor is further configured to calculate the representativeness score based on a number of times that a keyword was used in the media content. 
     
     
       9. The apparatus according to  claim 8 , wherein the media content processor is further configured to extract the keyword based on natural language processing and to analyze the keyword. 
     
     
       10. The apparatus according to  claim 1 , wherein the service provider is further configured to provide the selected each piece of the media content to the user through a web page. 
     
     
       11. The apparatus according to  claim 1  wherein the service provider is further configured to select the selected each piece of the media content by assigning weights to voting rights based on personal information of each of a plurality of users. 
     
     
       12. The apparatus according to  claim 1 , wherein the media content comprises content posted on the SNS server by the user or a friend of the user on the SNS. 
     
     
       13. A method to select and provide media content on a social network service (SNS), the method comprising:
 searching media content related to a user accessing an SNS server, wherein the media content comprises either one or both of an image and text; 
 calculating a representativeness score for each piece of the media content as a weighted sum of any combination of any two or more of a number of likes, a number of shares, and information associated with a friend of the user on the SNS who liked or shared the media content, wherein weights of the weighted sum are based on a number of words in a comment and a number of friends who wrote comments; 
 selecting the each piece of the media content having the representative score greater than or equal to a threshold; 
 grouping the selected each piece of the media content using a K-means clustering algorithm; and 
 providing the grouped selected each piece of the media content to the user. 
 
     
     
       14. The method according to  claim 13 , wherein the text comprises a title of the media content, a body of the media content, or a comment of the media content, and
 wherein the selecting the selected each piece of the media content further comprises selecting the selected each piece of the media content using metadata comprising at least one of creation time information, edited time information, locational information, a file name, a file format, the number of likes, the number of shares of the media content, or the information associated with the friend of the user on the SNS who liked or shared the media content. 
 
     
     
       15. The method according to  claim 14 , wherein the representative score is further determined by analyzing the text or the metadata of the media content. 
     
     
       16. The method according to  claim 13 , wherein the selected each piece of the media content is provided to the user through a web page. 
     
     
       17. The method according to  claim 13 , wherein the selected each piece of the media content is selected by assigning weights to voting rights based on personal information of each of a plurality of users. 
     
     
       18. The method according to  claim 13 , wherein the media content comprises content posted on the SNS server by the user or a friend of the user on the SNS.

Cited by (0)

No later patents cite this yet.

References (0)

No backward citations on record.